Analysis and Prediction of Dammed Water Level in a Hydropower Reservoir Using Machine Learning and Persistence-Based Techniques

Research areas:

• Applications - Weather forecasting

Year:

2020

Type of Publication:

Article

Keywords:

dammed water level, hydropower reservoirs, detrended fluctuation analysis, ARMA models, machine learning regressors, reservoir management

Authors:

• Castillo-Botón, Carlos
• Casillas-Pérez, David
• Casanova-Mateo, Carlos
• Moreno-Saavedra, L. M.
• Morales-Díaz, B.
• Sanz-Justo, J.
• Gutiérrez, Pedro Antonio
• Salcedo-Sanz, Sancho

Journal:

Water

Volume:

12

Number:

6

Pages:

1528

Month:

May

ISSN:

2073-4441

BibTex:

@article{CarlosCastillo2020Water, author = "Carlos Castillo-Bot{\'o}n and David Casillas-P{\'e}rez and Carlos Casanova-Mateo and L.M. Moreno-Saavedra and B. Morales-D{\'i}az and J. Sanz-Justo and Pedro Antonio Guti{\'e}rrez and Sancho Salcedo-Sanz", abstract = "This paper presents long- and short-term analyses and predictions of dammed water level in a hydropower reservoir. The long-term analysis was carried out by using techniques such as detrended fluctuation analysis, auto-regressive models, and persistence-based algorithms. On the other hand, the short-term analysis of the dammed water level in the hydropower reservoir was modeled as a prediction problem, where machine learning regression techniques were studied. A set of models, including different types of neural networks, Support Vector regression, or Gaussian processes was tested. Real data from a hydropower reservoir located in Galicia, Spain, qwew considered, together with predictive variables from upstream measuring stations. We show that the techniques presented in this paper offer an excellent tool for the long- and short-term analysis and prediction of dammed water level in reservoirs for hydropower purposes, especially important for the management of water resources in areas with hydrology stress, such as Spain.", awards = "JCR(2020): 3.103 Position: 39/98 (Q2) Category: WATER RESOURCES -- SCIE", comments = "JCR(2020): 3.103 Position: 39/98 (Q2) Category: WATER RESOURCES -- SCIE", doi = "10.3390/w12061528", issn = "2073-4441", journal = "Water", keywords = "dammed water level, hydropower reservoirs, detrended fluctuation analysis, ARMA models, machine learning regressors, reservoir management", month = "May", note = "JCR(2020): 3.103 Position: 39/98 (Q2) Category: WATER RESOURCES -- SCIE", number = "6", pages = "1528", title = "{A}nalysis and {P}rediction of {D}ammed {W}ater {L}evel in a {H}ydropower {R}eservoir {U}sing {M}achine {L}earning and {P}ersistence-{B}ased {T}echniques", url = "dx.doi.org/10.3390/w12061528", volume = "12", year = "2020", }

Note:

JCR(2020): 3.103 Position: 39/98 (Q2) Category: WATER RESOURCES -- SCIE

Abstract:

This paper presents long- and short-term analyses and predictions of dammed water level in a hydropower reservoir. The long-term analysis was carried out by using techniques such as detrended fluctuation analysis, auto-regressive models, and persistence-based algorithms. On the other hand, the short-term analysis of the dammed water level in the hydropower reservoir was modeled as a prediction problem, where machine learning regression techniques were studied. A set of models, including different types of neural networks, Support Vector regression, or Gaussian processes was tested. Real data from a hydropower reservoir located in Galicia, Spain, qwew considered, together with predictive variables from upstream measuring stations. We show that the techniques presented in this paper offer an excellent tool for the long- and short-term analysis and prediction of dammed water level in reservoirs for hydropower purposes, especially important for the management of water resources in areas with hydrology stress, such as Spain.

Comments:

JCR(2020): 3.103 Position: 39/98 (Q2) Category: WATER RESOURCES -- SCIE